📦 QwenLM/qwen-code：运行在终端中的开源 AI 编程 Agent

• 开箱即用的 Agent 能力 —— 提供 Auto-Memory、Auto-Skills、SubAgents、Agent Teams 和 MCP。动态工作流，零配置。
  • 内外完全开源 —— 框架和 Qwen 模型均为开源项目，并共同演进。没有厂商锁定。
  • 多协议支持 —— 支持 OpenAI、Anthropic、Gemini 和 Qwen API。可使用任意第三方服务商或本地模型（Ollama / vLLM），并可在运行时切换。
  • 超越终端 —— 提供 IDE 插件、桌面应用、Daemon 模式、SDK，以及 IM 机器人（Telegram / 钉钉 / 微信 / 飞书）。

提示

Qwen Code 正在积极利用自身进行迭代——使用自己的 Agent 和模型创建 Issue、提交 PR、审查代码和运行测试。由社区驱动，也由 AI 驱动。

Linux / macOS：

curl -fsSL https://qwen-code-assets.oss-cn-hangzhou.aliyuncs.com/installation/install-qwen-standalone.sh | bash

Windows：

irm https://qwen-code-assets.oss-cn-hangzhou.aliyuncs.com/installation/install-qwen-standalone.ps1 | iex

安装后请重启终端，以确保环境变量生效。

NPM / Homebrew

NPM（需要 Node.js 22+）：

npm install -g @qwen-code/qwen-code@latest

Homebrew（macOS / Linux）：

qwen          # 启动交互式终端 UI
# 在会话中：
/auth         # 配置服务商和 API 密钥

有关详细设置，请参阅认证指南和设置参考。

SDK 示例（Python）

import asyncio

from qwen_code_sdk import is_sdk_result_message, query


async def main() -> None:
    result = query(
        "Summarize the repository layout.",
        {
            "cwd": "/path/to/project",
            "path_to_qwen_executable": "qwen",
        },
    )

    async for message in result:
        if is_sdk_result_message(message):
            print(message["result"])


asyncio.run(main())

如果你熟悉 Claude Code，那么你已经熟悉 Qwen Code——而且它还不止于此。我们投入了大量精力，致力于让 Qwen Code 在功能上与 Claude Code 达到同等水平，并全面提升功能广度和可靠性。

• Qwen Code Desktop —— 面向 macOS、Windows 和 Linux 的官方桌面应用

• AionUi —— 面向包括 Qwen Code 在内的命令行 AI 工具的现代 GUI

• Gemini CLI Desktop —— 面向 Qwen Code 的跨平台桌面端 / Web / 移动端 UI

• 🦞 Qwen Code Claw —— 让其他 Agent（Claude、Codex 等）通过 ACP 将编程任务委派给 Qwen Code。将以下提示词粘贴到你的 Agent 中：

  Use Qwen Code as a coding agent. First, fetch and read this skill reference: https://raw.githubusercontent.com/QwenLM/qwen-code/refs/heads/main/.qwen/skills/qwen-code-claw/SKILL.md Then follow the instructions inside to install, authenticate, and use Qwen Code via acpx for all coding tasks.

欢迎贡献！请参阅 CONTRIBUTING.md 了解相关指南。

本项目最初基于 Google Gemini CLI v0.8.2。我们衷心感谢 Gemini CLI 团队的出色工作。自 Qwen Code v0.1 起，我们停止与上游同步，开始独立开发，将其打造为一个支持多协议、多平台的 Agent 框架，并深度集成 Qwen 模型及更多模型。

• Agentic out of the box — Auto-Memory, Auto-Skills, SubAgents, Agent Teams, and MCP. Dynamic workflows, zero setup.
  • Open-source, inside and out — The framework and the Qwen models are open-source. They evolve together. No vendor lock-in.
  • Multi-protocol — Supports OpenAI, Anthropic, Gemini, and Qwen APIs. Any third-party provider or local model (Ollama / vLLM). Switch at runtime.
  • Beyond the terminal — IDE plugins, Desktop app, daemon mode, SDKs, and IM bots (Telegram / DingTalk / WeChat / Feishu).

Tip

Qwen Code is actively iterating on itself — using its own agent and models to file issues, submit PRs, review code, and run tests. Powered by the community, driven by AI.

Linux / macOS:

curl -fsSL https://qwen-code-assets.oss-cn-hangzhou.aliyuncs.com/installation/install-qwen-standalone.sh | bash

Windows:

irm https://qwen-code-assets.oss-cn-hangzhou.aliyuncs.com/installation/install-qwen-standalone.ps1 | iex

Restart your terminal after installation to ensure environment variables take effect.

NPM / Homebrew

NPM (requires Node.js 22+):

npm install -g @qwen-code/qwen-code@latest

Homebrew (macOS / Linux):

qwen          # Launch interactive terminal UI
# Inside the session:
/auth         # Configure your provider and API key

See the Authentication Guide and Settings Reference for detailed setup.

import asyncio

from qwen_code_sdk import is_sdk_result_message, query


async def main() -> None:
    result = query(
        "Summarize the repository layout.",
        {
            "cwd": "/path/to/project",
            "path_to_qwen_executable": "qwen",
        },
    )

    async for message in result:
        if is_sdk_result_message(message):
            print(message["result"])


asyncio.run(main())

If you know Claude Code, you already know Qwen Code — and then some. We've put significant effort into bringing Qwen Code to feature parity with Claude Code, improving both breadth and reliability across the board.

• Qwen Code Desktop — Official desktop app for macOS, Windows, and Linux

• AionUi — A modern GUI for command-line AI tools including Qwen Code

• Gemini CLI Desktop — A cross-platform desktop/web/mobile UI for Qwen Code

• 🦞 Qwen Code Claw — Let other agents (Claude, Codex, etc.) delegate coding tasks to Qwen Code via ACP. Paste this prompt into your agent:

  Use Qwen Code as a coding agent. First, fetch and read this skill reference: https://raw.githubusercontent.com/QwenLM/qwen-code/refs/heads/main/.qwen/skills/qwen-code-claw/SKILL.md Then follow the instructions inside to install, authenticate, and use Qwen Code via acpx for all coding tasks.

Contributions are welcome! See CONTRIBUTING.md for guidelines.

This project was originally based on Google Gemini CLI v0.8.2. We gratefully acknowledge the Gemini CLI team's excellent work. Starting from Qwen Code v0.1, we stopped syncing with upstream and began independent development as a multi-protocol, multi-platform agent framework with deep integrations for Qwen models and beyond.